Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

51
/ 100
Established

This tool helps you analyze the 3D movement of multiple people in real-time from standard video feeds. It takes video or live camera input and outputs the precise 3D locations of key body points like ears, eyes, shoulders, and knees for each person. This is ideal for researchers, analysts, or developers working on human motion studies, sports analytics, or physical therapy.

685 stars. No commits in the last 6 months.

Use this if you need to track and understand the full 3D posture and movement of individuals in a video stream with high accuracy and low latency.

Not ideal if you only need 2D pose estimation or are working with still images rather than dynamic video.

human-motion-analysis sports-science biomechanics activity-recognition physical-therapy
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

685

Forks

138

Language

Python

License

Apache-2.0

Last pushed

Nov 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.